{"id":"https://openalex.org/W7135065920","doi":"https://doi.org/10.1016/j.ipm.2026.104720","title":"Explicit geometric relationships under limited spatial reference points guide 3D visual grounding","display_name":"Explicit geometric relationships under limited spatial reference points guide 3D visual grounding","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135065920","doi":"https://doi.org/10.1016/j.ipm.2026.104720"},"language":"en","primary_location":{"id":"doi:10.1016/j.ipm.2026.104720","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104720","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing & Management","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.ipm.2026.104720","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124749141","display_name":"Zongshun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongshun Wang","raw_affiliation_strings":["School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China"],"raw_orcid":"https://orcid.org/0009-0004-3644-0988","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128809011","display_name":"Ce Li","orcid":null},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ce Li","raw_affiliation_strings":["School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou Gansu, 730050, China"],"raw_orcid":"https://orcid.org/0000-0002-4627-6112","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]},{"raw_affiliation_string":"School of Microelectronics Industry-education Integration, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124724964","display_name":"Jialin Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Ma","raw_affiliation_strings":["School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China"],"raw_orcid":"https://orcid.org/0000-0003-3255-4158","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128850972","display_name":"Zhiqiang Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Feng","raw_affiliation_strings":["School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China"],"raw_orcid":"https://orcid.org/0009-0007-8908-5635","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pengcheng Wang","orcid":"https://orcid.org/0009-0004-1906-0967"},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Wang","raw_affiliation_strings":["School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China"],"raw_orcid":"https://orcid.org/0009-0004-1906-0967","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128891955","display_name":"Xiaodong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China"],"raw_orcid":"https://orcid.org/0009-0001-4928-7263","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128825130","display_name":"Limei Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I22716506","display_name":"Lanzhou University of Technology","ror":"https://ror.org/03panb555","country_code":"CN","type":"education","lineage":["https://openalex.org/I22716506"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Limei Xiao","raw_affiliation_strings":["School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China"],"raw_orcid":"https://orcid.org/0000-0002-0612-4982","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, Lanzhou University of Technology, Lanzhou Gansu, 730050, China","institution_ids":["https://openalex.org/I22716506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5128809011"],"corresponding_institution_ids":["https://openalex.org/I22716506"],"apc_list":{"value":3220,"currency":"USD","value_usd":3220},"apc_paid":{"value":3220,"currency":"USD","value_usd":3220},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31351894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"63","issue":"6","first_page":"104720","last_page":"104720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9047999978065491,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9047999978065491,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.023900000378489494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01549999974668026,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5576000213623047},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.527999997138977},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.45980000495910645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45590001344680786},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.37880000472068787},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.367900013923645},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.3619000017642975},{"id":"https://openalex.org/keywords/distance-matrix","display_name":"Distance matrix","score":0.3596000075340271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7243000268936157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7232000231742859},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5691999793052673},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5576000213623047},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.527999997138977},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.45980000495910645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.37880000472068787},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3411000072956085},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.30090001225471497},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C123403432","wikidata":"https://www.wikidata.org/wiki/Q654068","display_name":"Visibility","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.ipm.2026.104720","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104720","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing & Management","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.ipm.2026.104720","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.ipm.2026.104720","pdf_url":null,"source":{"id":"https://openalex.org/S174847851","display_name":"Information Processing & Management","issn_l":"0306-4573","issn":["0306-4573","1873-5371"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information Processing & Management","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4922841191291809}],"awards":[{"id":"https://openalex.org/G4343139920","display_name":null,"funder_award_id":"62363025","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6550740576","display_name":null,"funder_award_id":"23YFFA0064","funder_id":"https://openalex.org/F4320336616","funder_display_name":"Science and Technology Program of Gansu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324678","display_name":"Lanzhou Science and Technology Bureau","ror":"https://ror.org/030q46522"},{"id":"https://openalex.org/F4320325900","display_name":"Gansu Education Department","ror":null},{"id":"https://openalex.org/F4320336616","display_name":"Science and Technology Program of Gansu Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3039448353","https://openalex.org/W4389519030","https://openalex.org/W4396830596","https://openalex.org/W4398794745","https://openalex.org/W4400235858","https://openalex.org/W4405625226","https://openalex.org/W4410230567","https://openalex.org/W4410349385","https://openalex.org/W4411051196","https://openalex.org/W4411203536","https://openalex.org/W4413144643","https://openalex.org/W4413156088"],"related_works":[],"abstract_inverted_index":{"Three-Dimensional":[0],"Visual":[1,59],"Grounding":[2,60],"(3DVG)":[3],"aims":[4],"to":[5,27,100],"locate":[6],"objects":[7,26],"in":[8,38],"3D":[9,58],"scenes":[10],"based":[11,118],"on":[12,20,119,148],"natural":[13],"language":[14],"queries.":[15],"Existing":[16],"methods":[17],"typically":[18],"rely":[19],"absolute":[21],"position":[22],"encoding":[23],"of":[24,69,78,94,123,132],"global":[25],"model":[28],"spatial":[29,40,79],"relationships":[30,80],"for":[31,81],"target":[32],"localization.":[33],"However,":[34],"this":[35],"often":[36],"results":[37],"inadequate":[39],"understanding":[41],"and":[42,89,151,165,168],"redundant":[43],"or":[44],"invalid":[45],"encoding.":[46],"To":[47],"address":[48],"these":[49,95],"limitations,":[50],"we":[51,104],"propose":[52],"the":[53,76,87,120,130,142],"Relative":[54],"K-object":[55],"Fusion":[56],"Perception":[57],"(3DRelKG)":[61],"framework.":[62],"By":[63],"dynamically":[64],"sampling":[65],"a":[66,106],"limited":[67],"number":[68],"scene":[70,101],"reference":[71,96],"points,":[72],"our":[73,155],"approach":[74,127],"enhances":[75],"modeling":[77],"localization":[82],"targets":[83],"by":[84,162,172],"learning":[85],"only":[86],"positional":[88],"relative":[90],"spherical":[91],"geometric":[92],"features":[93],"points":[97],"with":[98],"respect":[99],"objects.":[102],"Additionally,":[103],"introduce":[105],"heterogeneous":[107,124,145],"feature":[108],"fusion":[109],"module,":[110],"whose":[111],"core":[112],"is":[113],"an":[114],"information":[115],"interaction":[116,135],"mechanism":[117],"similarity":[121,143],"matrix":[122],"features.":[125,146],"This":[126],"naturally":[128],"avoids":[129],"problem":[131],"unreliable":[133],"attention":[134],"weights":[136],"that":[137,154],"arise":[138],"from":[139],"directly":[140],"calculating":[141],"between":[144],"Experiments":[147],"ScanRefer,":[149],"SR3D,":[150],"NR3D":[152],"demonstrate":[153],"method":[156],"outperforms":[157],"state-of-the-art":[158],"models,":[159],"improving":[160],"accuracy":[161],"2.3%,":[163],"4.3%,":[164],"2.1%,":[166],"respectively,":[167],"increasing":[169],"inference":[170],"speed":[171],"43.8%.":[173]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-03-13T00:00:00"}